Title :
Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Author :
Zhen Cui ; Wen Li ; Dong Xu ; Shiguang Shan ; Xilin Chen
Author_Institution :
Key Lab. of Intell. Inf. Process., Inst. of Comput. Technol., Beijing, China
Abstract :
In many real-world face recognition scenarios, face images can hardly be aligned accurately due to complex appearance variations or low-quality images. To address this issue, we propose a new approach to extract robust face region descriptors. Specifically, we divide each image (resp. video) into several spatial blocks (resp. spatial-temporal volumes) and then represent each block (resp. volume) by sum-pooling the nonnegative sparse codes of position-free patches sampled within the block (resp. volume). Whitened Principal Component Analysis (WPCA) is further utilized to reduce the feature dimension, which leads to our Spatial Face Region Descriptor (SFRD) (resp. Spatial-Temporal Face Region Descriptor, STFRD) for images (resp. videos). Moreover, we develop a new distance metric learning method for face verification called Pairwise-constrained Multiple Metric Learning (PMML) to effectively integrate the face region descriptors of all blocks (resp. volumes) from an image (resp. a video). Our work achieves the state-of-the-art performances on two real-world datasets LFW and YouTube Faces (YTF) according to the restricted protocol.
Keywords :
face recognition; learning (artificial intelligence); principal component analysis; PMML; SFRD; STFRD; WPCA; YTF; YouTube faces; appearance variations; distance metric learning method; face images; face recognition; face verification; feature dimension reduction; low-quality images; nonnegative sparse codes; pairwise-constrained multiple metric learning; position-free patches; principal component analysis; real-world datasets LFW; restricted protocol; robust face region descriptor fusion; spatial blocks; spatial face region descriptor; spatial-temporal face region descriptor; Encoding; Face; Face recognition; Feature extraction; Measurement; Principal component analysis; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Conference_Location :
Portland, OR
DOI :
10.1109/CVPR.2013.456